You will design, build, and operate the foundational compute infrastructure, including hardware, firmware, and virtualization layers. You are responsible for managing the fleet, ensuring system reliability, and bridging the gap between physical hardware and production software.
You will own the end-to-end inference infrastructure, including model placement, serving runtimes, and performance benchmarking for production workloads. You are responsible for turning complex inference expertise into programmatic software to automate deployment decisions and ensure system reliability.
You will own the end-to-end network path from customer edge to GPU workloads, including routing, segmentation, and secure private access. You will also be responsible for building scalable network automation and observability to ensure reliable production outcomes.
